Verification of liveness data for identity proofing

1 . A method, comprising:

receiving, by a first device and from a second device, a video of a first subject and indications of one or more frames from the video selected by the second device;

selecting, by the first device, two or more additional frames from the video, wherein the two or more additional frames are selected at non-sequential time intervals relative to the one or more frames selected by the second device and are disjoint from the one or more frames selected by the second device;

generating, by the first device, a first confidence score that the video was captured in a single take based on a comparison between the one or more frames selected by the second device and the two or more additional frames;

generating, by the first device, a request for proofing an identity of the first subject, the request comprising the first confidence score; and

transmitting, by the first device, the request for proofing the identity to a third device.

2 . The method of claim 1 , further comprising:

receiving, by the first device and from the second device, an image of a second subject; and

generating, by the first device, a second confidence score that the first subject and the second subject are matching, wherein the request for proofing the identity also comprises the image and the second confidence score.

3 . The method of claim 1 , wherein the two or more additional frames are randomly selected from the video distinct from the indications of one or more frames selected by the second device.

4 . The method of claim 1 , wherein the two or more additional frames show a face of the first subject.

5 . The method of claim 1 , wherein the two or more additional frames are at least a threshold time between each other.

6 . The method of claim 1 , wherein the two or more additional frames are within at least a threshold time from a frame of the one or more frames selected by the second device.

7 . The method of claim 1 , further comprising receiving, by the first device, an identification from the third device provisioned for the second device, in response to the third device approving the request for proofing the identity of the first subject.

8 . The method of claim 7 , further comprising transmitting, by the first device, the identification to the second device, in response to receiving the identification from the third device.

9 . The method of claim 1 , wherein a single take represents the video having been captured in a single, continuous instance of time.

10 . The method of claim 1 , wherein the video includes the first subject performing a gesture.

11 . A method, comprising:

accessing, by a first device, a video of a first subject performing a gesture;

selecting, by the first device, one or more frames from the video; and

transmitting, by the first device, the video and indications of the one or more frames selected by the first device to a second device for the second device to determine a confidence score indicating whether the video was captured in a single take based on a comparison between the one or more frames selected by the first device and two or more additional frames of the video selected by the second device, wherein the two or more additional frames are selected at non-sequential time intervals relative to the one or more frames selected by the first device and are disjoint from the one or more frames selected by the first device.

12 . The method of claim 11 , further comprising:

accessing, by the first device, an image of a second subject; and

transmitting, by the first device, the image of the second subject to the second device for determining whether the first subject and the second subject are matching.

13 . The method of claim 11 , wherein accessing the video comprises capturing video data from a camera of the first device.

14 . The method of claim 11 , wherein the one or more frames selected by the first device are randomly selected from the video.

15 . The method of claim 11 , wherein the one or more frames selected by the first device show a face of the first subject.

16 . The method of claim 11 , wherein the one or more frames selected by the first device are at least a threshold time between each other.

17 . The method of claim 11 , further comprising receiving, by the first device, an identification provisioned for the first device by a third device.

18 . The method of claim 17 , further comprising binding, by the first device, the identification to the first device.

19 . The method of claim 11 , wherein the indications of the one or more frames are one or more timestamps of the video corresponding to a respective frame of the one or more frames.

20 . A first device, comprising:

a processor; and

a memory storing machine-readable instructions that, when executed by the processor, cause the processor to perform operations comprising:

receiving, by the first device and from a second device, a video of a first subject and indications of one or more frames from the video selected by the second device;

selecting, by the first device, two or more additional frames from the video, wherein the two or more additional frames are selected at non-sequential time intervals relative to the one or more frames selected by the second device and are disjoint from the one or more frames selected by the second device;

generating, by the first device, a confidence score that the video was captured in a single take based on a comparison between the one or more frames selected by the second device and the two or more additional frames;

generating, by the first device, a request for proofing an identity of the first subject, the request comprising the confidence score; and

transmitting, by the first device, the request for proofing the identity to a third device.